configs/top_transformer_340M.json

{
    "attention_bias": false,
    "bos_token_id": 1,
    "eos_token_id": 2,
    "fuse_cross_entropy": true,
    "fuse_norm": true,
    "hidden_act": "swish",
    "hidden_size": 1024,
    "initializer_range": 0.006,
    "max_position_embeddings": 8192,
    "model_type": "top_transformer",
    "num_heads": 16,
    "num_hidden_layers": 24,
    "norm_eps": 1e-06,
    "tie_word_embeddings": false,
    "use_cache": true,
    "vocab_size": 32000,
    "use_top_loss": true,
    "top_window_size": 4096
}